Re: [PATCH 4/5] archive: do not read .gitattributes in working directory

From

Nguyen Thai Ngoc Duy <pclouds@gmail.com>

Date

Apr 16, 2009, 12:38 UTC

Message-ID

<fcaeb9bf0904160538w4a826c57r40e9cf1c52b0b6ff@mail.gmail.com>

In-Reply-To

<fcaeb9bf0904160350m14dce828oe88bda6562d98f48@mail.gmail.com>

On Thu, Apr 16, 2009 at 8:50 PM, Nguyen Thai Ngoc Duy <pclouds@gmail.com> wrote:

> I was thinking about loading .gitattributes inside write_archive_entry
> too, to avoid calling read_tree_recursive twice, but it requires
> .gitattributes to be traversed first. Won't work if there are files
> .abc, .def...
>
> If read_tree_recusive() expose its tree to read_tree_fn_t, we can then
> look ahead and load .gitattributes, but that requires changing
> read_tree_fn_t interface. I'll see if it's feasible to make a
> customized read_tree_recusive() just for archive.c

-- 
Duy


diff --git a/archive.c b/archive.c
index 0ce628b..8df53a8 100644
--- a/archive.c
+++ b/archive.c
@@ -97,6 +97,43 @@ struct archiver_context {
 	write_archive_entry_fn_t write_entry;
 };
 
+static int read_gitattr_to_index(struct tree *tree, const char *base, int baselen, struct archiver_args *args)
+{
+	struct tree_desc desc;
+	struct name_entry entry;
+	struct cache_entry *ce;
+	unsigned int size;
+	int pathlen;
+
+	if (parse_tree(tree))
+		return -1;
+
+	init_tree_desc(&desc, tree->buffer, tree->size);
+
+	while (tree_entry(&desc, &entry)) {
+		if (S_ISDIR(entry.mode) || S_ISGITLINK(entry.mode))
+			continue;
+		if (strcmp(entry.path, GITATTRIBUTES_FILE))
+			continue;
+		pathlen = tree_entry_len(entry.path, entry.sha1);
+		baselen -= args->baselen; /* remove user prefix */
+		if (baselen)
+			baselen++; /* slash */
+		size = cache_entry_size(baselen + pathlen);
+		ce = xcalloc(1, size);
+		ce->ce_mode = create_ce_mode(entry.mode);
+		ce->ce_flags = create_ce_flags(baselen + pathlen, 0);
+		if (baselen) {
+			memcpy(ce->name, base + args->baselen, baselen-1);
+			ce->name[baselen-1] = '/';
+		}
+		memcpy(ce->name + baselen, entry.path, pathlen + 1);
+		hashcpy(ce->sha1, entry.sha1);
+		return add_cache_entry(ce, ADD_CACHE_OK_TO_ADD | ADD_CACHE_SKIP_DFCHECK);
+	}
+	return 0;
+}
+
 static int write_archive_entry(const unsigned char *sha1, const char *base,
 		int baselen, const char *filename, unsigned mode, int stage,
 		void *context)
@@ -119,11 +156,25 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 	strbuf_addstr(&path, filename);
 	path_without_prefix = path.buf + args->baselen;
 
-	setup_archive_check(check);
-	if (!git_checkattr(path_without_prefix, ARRAY_SIZE(check), check)) {
-		if (ATTR_TRUE(check[0].value))
-			return 0;
-		convert = ATTR_TRUE(check[1].value);
+	if (S_ISDIR(mode)) {
+		/*
+		 * we want to read .gitattributes before any entry is processed
+		 * so every time we get a directory entry, we look ahead to see
+		 * if there is .gitattributes and load it
+		 *
+		 * later when the directory is processed, .gitattributes is
+		 * already ready in index for git_checkattr()
+		 */
+		if (!args->worktree_attributes)
+			read_gitattr_to_index(lookup_tree(sha1), base, baselen, args);
+	}
+	else {
+		setup_archive_check(check);
+		if (!git_checkattr(path_without_prefix, ARRAY_SIZE(check), check)) {
+			if (ATTR_TRUE(check[0].value))
+				return 0;
+			convert = ATTR_TRUE(check[1].value);
+		}
 	}
 
 	if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
@@ -151,8 +202,6 @@ int write_archive_entries(struct archiver_args *args,
 		write_archive_entry_fn_t write_entry)
 {
 	struct archiver_context context;
-	struct unpack_trees_options opts;
-	struct tree_desc t;
 	int err;
 
 	if (args->baselen > 0 && args->base[args->baselen - 1] == '/') {
@@ -171,19 +220,9 @@ int write_archive_entries(struct archiver_args *args,
 	context.args = args;
 	context.write_entry = write_entry;
 
-	/*
-	 * Setup index and instruct attr to read index only
-	 */
 	if (!args->worktree_attributes) {
-		memset(&opts, 0, sizeof(opts));
-		opts.index_only = 1;
-		opts.head_idx = -1;
-		opts.src_index = &the_index;
-		opts.dst_index = &the_index;
-		opts.fn = oneway_merge;
-		init_tree_desc(&t, args->tree->buffer, args->tree->size);
-		if (unpack_trees(1, &t, &opts))
-			return -1;
+		/* read .gitattributes at root if any */
+		read_gitattr_to_index(args->tree, args->base, args->baselen, args);
 		git_attr_set_direction(GIT_ATTR_INDEX, &the_index);
 	}
 
@@ -209,13 +248,23 @@ static const struct archiver *lookup_archiver(const char *name)
 }
 
 static void parse_pathspec_arg(const char **pathspec,
-		struct archiver_args *ar_args)
+		struct archiver_args *ar_args,
+		const char *prefix)
 {
-	ar_args->pathspec = get_pathspec(ar_args->base, pathspec);
+	struct strbuf s = STRBUF_INIT;
+	if (ar_args->base)
+		strbuf_addstr(&s, ar_args->base);
+	if (prefix)
+		strbuf_addstr(&s, prefix);
+	ar_args->pathspec = get_pathspec(s.len ? s.buf : NULL, pathspec);
+	/*
+	 * s.buf must never be freed because
+	 * get_pathspec does not duplicate it
+	 */
 }
 
 static void parse_treeish_arg(const char **argv,
-		struct archiver_args *ar_args, const char *prefix)
+		struct archiver_args *ar_args)
 {
 	const char *name = argv[0];
 	const unsigned char *commit_sha1;
@@ -240,18 +289,6 @@ static void parse_treeish_arg(const char **argv,
 	if (tree == NULL)
 		die("not a tree object");
 
-	if (prefix) {
-		unsigned char tree_sha1[20];
-		unsigned int mode;
-		int err;
-
-		err = get_tree_entry(tree->object.sha1, prefix,
-				     tree_sha1, &mode);
-		if (err || !S_ISDIR(mode))
-			die("current working directory is untracked");
-
-		tree = parse_tree_indirect(tree_sha1);
-	}
 	ar_args->tree = tree;
 	ar_args->commit_sha1 = commit_sha1;
 	ar_args->commit = commit;
@@ -360,8 +397,8 @@ int write_archive(int argc, const char **argv, const char *prefix,
 	if (setup_prefix && prefix == NULL)
 		prefix = setup_git_directory();
 
-	parse_treeish_arg(argv, &args, prefix);
-	parse_pathspec_arg(argv + 1, &args);
+	parse_treeish_arg(argv, &args);
+	parse_pathspec_arg(argv + 1, &args, prefix);
 
 	git_config(git_default_config, NULL);